OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment.
Xize ChengTao JinLinjun LiWang LinXinyu DuanZhou ZhaoPublished in: CoRR (2023)
Keyphrases
- speech recognition
- multi modality
- multi modal
- medical images
- single modality
- hidden markov models
- speech signal
- speech processing
- pattern recognition
- information theoretic
- speech recognizer
- noisy environments
- language model
- image registration
- imaging modalities
- speech synthesis
- speaker identification
- speech recognition technology
- automatic speech recognition
- mutual information
- anatomical structures
- speech recognition systems
- image processing
- speech recognizers
- image intensity
- image analysis
- speech retrieval
- high dimensional
- isolated word
- video search
- b spline
- medical imaging
- speaker independent
- speaker dependent